{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:H45ZRETJFZP2LNQFYNSTTELTLN","short_pith_number":"pith:H45ZRETJ","schema_version":"1.0","canonical_sha256":"3f3b9892692e5fa5b605c3653991735b5e909f41d3705151e4657e27caf7b3fe","source":{"kind":"arxiv","id":"2301.09604","version":2},"attestation_state":"computed","paper":{"title":"FedExP: Speeding Up Federated Averaging via Extrapolation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Divyansh Jhunjhunwala, Gauri Joshi, Shiqiang Wang","submitted_at":"2023-01-23T18:10:22Z","abstract_excerpt":"Federated Averaging (FedAvg) remains the most popular algorithm for Federated Learning (FL) optimization due to its simple implementation, stateless nature, and privacy guarantees combined with secure aggregation. Recent work has sought to generalize the vanilla averaging in FedAvg to a generalized gradient descent step by treating client updates as pseudo-gradients and using a server step size. While the use of a server step size has been shown to provide performance improvement theoretically, the practical benefit of the server step size has not been seen in most existing works. In this work"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2301.09604","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-01-23T18:10:22Z","cross_cats_sorted":[],"title_canon_sha256":"2fbe8e78e84ced2aae565b49adbcd87ea2c7c4cf5b040a1ed8558ed0106fdc82","abstract_canon_sha256":"c14851ab1bfb634b3fc6c6b23241be5b81ee84cdf3ff2412ac858ad2b3065cad"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:48:26.144229Z","signature_b64":"20uAT7R3lcV2Zh4s51UflAoWSz+Sa6wimR5BrhzHwSfjAxp7236z4Mh2EepLsjyyiS9wiFgS5YseQv+Fbi+pCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3f3b9892692e5fa5b605c3653991735b5e909f41d3705151e4657e27caf7b3fe","last_reissued_at":"2026-07-05T05:48:26.143811Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:48:26.143811Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FedExP: Speeding Up Federated Averaging via Extrapolation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Divyansh Jhunjhunwala, Gauri Joshi, Shiqiang Wang","submitted_at":"2023-01-23T18:10:22Z","abstract_excerpt":"Federated Averaging (FedAvg) remains the most popular algorithm for Federated Learning (FL) optimization due to its simple implementation, stateless nature, and privacy guarantees combined with secure aggregation. Recent work has sought to generalize the vanilla averaging in FedAvg to a generalized gradient descent step by treating client updates as pseudo-gradients and using a server step size. While the use of a server step size has been shown to provide performance improvement theoretically, the practical benefit of the server step size has not been seen in most existing works. In this work"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.09604","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2301.09604/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2301.09604","created_at":"2026-07-05T05:48:26.143867+00:00"},{"alias_kind":"arxiv_version","alias_value":"2301.09604v2","created_at":"2026-07-05T05:48:26.143867+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.09604","created_at":"2026-07-05T05:48:26.143867+00:00"},{"alias_kind":"pith_short_12","alias_value":"H45ZRETJFZP2","created_at":"2026-07-05T05:48:26.143867+00:00"},{"alias_kind":"pith_short_16","alias_value":"H45ZRETJFZP2LNQF","created_at":"2026-07-05T05:48:26.143867+00:00"},{"alias_kind":"pith_short_8","alias_value":"H45ZRETJ","created_at":"2026-07-05T05:48:26.143867+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2410.15368","citing_title":"Tighter Performance Theory of FedExProx","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/H45ZRETJFZP2LNQFYNSTTELTLN","json":"https://pith.science/pith/H45ZRETJFZP2LNQFYNSTTELTLN.json","graph_json":"https://pith.science/api/pith-number/H45ZRETJFZP2LNQFYNSTTELTLN/graph.json","events_json":"https://pith.science/api/pith-number/H45ZRETJFZP2LNQFYNSTTELTLN/events.json","paper":"https://pith.science/paper/H45ZRETJ"},"agent_actions":{"view_html":"https://pith.science/pith/H45ZRETJFZP2LNQFYNSTTELTLN","download_json":"https://pith.science/pith/H45ZRETJFZP2LNQFYNSTTELTLN.json","view_paper":"https://pith.science/paper/H45ZRETJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2301.09604&json=true","fetch_graph":"https://pith.science/api/pith-number/H45ZRETJFZP2LNQFYNSTTELTLN/graph.json","fetch_events":"https://pith.science/api/pith-number/H45ZRETJFZP2LNQFYNSTTELTLN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H45ZRETJFZP2LNQFYNSTTELTLN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H45ZRETJFZP2LNQFYNSTTELTLN/action/storage_attestation","attest_author":"https://pith.science/pith/H45ZRETJFZP2LNQFYNSTTELTLN/action/author_attestation","sign_citation":"https://pith.science/pith/H45ZRETJFZP2LNQFYNSTTELTLN/action/citation_signature","submit_replication":"https://pith.science/pith/H45ZRETJFZP2LNQFYNSTTELTLN/action/replication_record"}},"created_at":"2026-07-05T05:48:26.143867+00:00","updated_at":"2026-07-05T05:48:26.143867+00:00"}